© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25053
    Prev
    Next
    INDEX
    Explanations

    kidnapped or abducted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     massac
    -0.10
     euth
    -0.10
     hunted
    -0.09
     hunt
    -0.09
     Crawford
    -0.09
     betrayed
    -0.09
     Adv
    -0.08
     arrival
    -0.08
    arrival
    -0.08
     cowboy
    -0.08
    POSITIVE LOGITS
     abduction
    0.27
     abducted
    0.24
     disappearance
    0.22
     kidnapping
    0.22
     disappear
    0.22
     kidnapped
    0.22
     disappeared
    0.21
     disappearing
    0.20
     kidn
    0.19
     vanished
    0.17
    Activations Density 0.235%

    No Known Activations